render-deploy

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to ask for and embed Render API keys verbatim into config files, CLI commands, and MCP headers (e.g., Authorization: Bearer <YOUR_API_KEY> and inserting it into ~/.cursor/mcp.json or CLI commands), which requires the LLM to handle secrets directly and creates an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires analyzing and reading user Git repositories hosted on third-party providers (e.g., GitHub/GitLab/Bitbucket via git remote/get-url, create_web_service(repo:...), and the Dashboard deeplink that reads render.yaml from the repo), which are untrusted/user-generated sources whose contents directly drive deployment decisions and actions.